Ollama Local AI

FreeRouter Team

Kupovina unutar aplikacije

O aplikaciji

🚀 Ollama Local AI is a powerful Ollama Android app for developers integrating local Large Language Models (LLMs) into IDE workflows. Turn your Android device into a secure, ultra-fast, switchable local-network OpenAI-compatible LLM proxy powered by local models and llama.cpp engine support.

📱 Point Cursor, VS Code, Antigravity, Windsurf, or any modern coding assistant directly to your phone's LAN IP address. Use Ollama, llama.cpp local models, cloud APIs, or custom API keys without configuring multiple endpoints on your development machine.

🔒 100% On-Device: your models, keys, requests, and data remain secure on your own Android device — no third-party service and no external relay.

⚡ Key Features

🧠 Local LLM On-Device: run local AI models directly on your phone with llama.cpp engine support, no internet required

💬 Chat Mode: full chat sessions with local models or cloud APIs including OpenAI, Claude, and more — switch anytime

🎨 Canvas Mode: build and test websites inside chat, watch AI construct them live

🌐 WebX Preview: instantly preview websites built by Ollama or local AI, viewable from any browser on your network

🖥️ Cross-Device WebUI Access: open your chat WebUI from phone, tablet, or PC

🖥️ Zero-Config Local Hosting: runs an optimized embedded HTTP server (NanoHTTPD) directly on Android

🔌 OpenAI-Compatible API: standard endpoints (/v1/chat/completions, /v1/models, /health) for drop-in compatibility

🔄 Instant Provider Switching: save configurations for Ollama, llama.cpp, NVIDIA, OpenAI, Claude, Hugging Face, and custom endpoints — switch in one click

🚦 Faster, Safer Proxy Routing: optimized local AI proxy routing with per-provider timeouts and rate limits

🔀 Local Pool, Failover, and Round Robin: distribute requests across local models and providers for reliable AI routing

📡 LAN Master/Worker Pairing: link Android phones and devices into a private local AI network

🌐 Multi-Device Cluster Support: connect phones and devices into one local LLM inference cluster

🤖 Smart Multi-Agent Orchestration: coordinate multiple AI agents, providers, tools, and tasks

🎞️ Live Streaming Agent Stages: view agent progress and stages in real time

💬 Session-Stable Chat Routing: keep chat sessions consistently routed across supported providers

📊 Traffic Observatory: monitor request flow, packet routing, performance statistics, and proxy diagnostics live

🧪 Improved Tool Lab: test AI tools, provider connections, API requests, and workflows

🖥️ Improved Web Console: manage local AI routing, chat, providers, tools, and diagnostics from your browser

🎨 Refined Material 3 Interface: clean, responsive Android interface for local AI development

🔋 Lazy Token Bucket Rate Limiting: battery-efficient traffic control with zero unnecessary background drain

🔐 Secure Encrypted Storage: API keys protected with AES-256 encrypted EncryptedSharedPreferences

🧵 Offloaded I/O: fluid Compose UI and high-performance routing via Coroutines and Dispatchers.IO

🛠️ Full IDE Support: optimized for Cursor, VS Code, Antigravity, Windsurf, OpenAI-compatible clients, scripts, and custom AI tools

🛣️More Beta features

⚙️ More local AI integrations, provider support, developer tools, and performance optimizations in development

❓ Why choose Ollama Local AI?

Chat, code, route, and preview with Ollama, llama.cpp local models, or cloud AI APIs — all from one secure Android app. Build private local LLM workflows, connect your IDE through LAN, and manage AI traffic without external relays.

🔥 Optimize your local AI and LLM development workflow today with Ollama Local AI!
This app is not affiliated with or endorsed by Ollama.

Šta je novo

• Add photos, camera shots, and files directly to chats
• Improved chat experience with quick prompts, smoother responses, and retry for failed messages
• Refreshed Auto Route with a compact Premium card and clearer unlock state
• Improved navigation stability and in-app announcements